Verified limit lookup

Claude Code Max 5× Prompt Limits

Claude Code Max 5× Prompt Limits, verified against Claude Code's official documentation with scope, implementation impact, caveats, and a direct check.

Verified Aug 22, 20261 official source
Quick answer

Claude Code documents average max 5× prompt estimate as Approximately 50–200 prompts every 5 hours. This tier also shares its limit with Claude consumer activity.

Verified Aug 22, 2026Official source

Current limits

ConstraintCurrent valueScopeVerified source
average Max 5× prompt estimateThis tier also shares its limit with Claude consumer activity.Approximately 50–200 prompts every 5 hoursMax 5×AnthropicAug 22, 2026

Why does this limit matter?

The broad range reflects how much code, context, tool work, and model compute each prompt requires.

This value is scoped to Max 5×; a different plan, runtime, model, endpoint, region, or account can produce a different effective constraint.

What should you check?

  1. Use /status before starting parallel agents and record which model is selected.
  2. Confirm the exact plan, model, runtime, endpoint, region, and account that serve the failing workload.
  3. Record the observed value, response headers or configuration, timestamp, and source without logging secrets.

Important caveats

  • Heavy Opus use and concurrent Claude Code instances reach the limit sooner than lighter Sonnet work.
  • Treat the official source and live account configuration as authoritative if they differ from this verified snapshot.
HyperObserve reports the documented platform constraint. Your application, SDK, gateway, provider, region, or account can impose a lower effective limit.
Related

Related references and tools

Found an outdated limit? Report it.